Accurate phase retrieval of complex 3D point spread functions with deep residual neural networks.

Phase retrieval, i.e., the reconstruction of phase information from intensity information, is a central problem in many optical systems. Imaging the emission from a point source such as a single molecule is one example. Here, we demonstrate that a deep residual neural net is able to quickly and accurately extract the hidden phase for general point spread functions (PSFs) formed by Zernike-type phase modulations. Five slices of the 3D PSF at different focal positions within a two micrometer range around the focus are sufficient to retrieve the first six orders of Zernike coefficients.

[1]  Butch Moomaw.  Camera technologies for low light imaging: overview and relative advantages. , 2013, Methods in cell biology.

[2]  Hong Guo,et al.  Wavefront reconstruction with artificial neural networks. , 2006, Optics express.

[3]  S. Stallinga,et al.  High precision wavefront control in point spread function engineering for single emitter localization. , 2018, Optics express.

[4]  E. Culurciello,et al.  Analyzing complex single molecule emission patterns with deep learning , 2018, Nature Methods.

[5]  Yonina C. Eldar,et al.  Phase Retrieval: An Overview of Recent Developments , 2015, ArXiv.

[6]  Tomer Michaeli,et al.  Deep-STORM: super-resolution single-molecule microscopy by deep learning , 2018, 1801.09631.

[7]  M. Gustafsson,et al.  Phase‐retrieved pupil functions in wide‐field fluorescence microscopy , 2004, Journal of microscopy.

[8]  Christophe Zimmer,et al.  Deep learning massively accelerates super-resolution localization microscopy , 2018, Nature Biotechnology.

[9]  Zhengjun Liu,et al.  A review of iterative phase retrieval for measurement and encryption , 2017 .

[10]  Jacob T. Robinson,et al.  Generalized method to design phase masks for 3D super-resolution microscopy. , 2019, Optics express.

[11]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[12]  S. Marchesini,et al.  X-ray image reconstruction from a diffraction pattern alone , 2003, physics/0306174.

[13]  Jun Tanida,et al.  Deep learning wavefront sensing. , 2019, Optics express.

[14]  W. E. Moerner,et al.  Azimuthal Polarization Filtering for Accurate, Precise, and Robust Single-Molecule Localization Microscopy , 2014, Nano letters.

[15]  Martin J Booth,et al.  Image based adaptive optics through optimisation of low spatial frequencies. , 2007, Optics express.

[16]  R. Gerchberg.  A practical algorithm for the determination of phase from image and diffraction plane pictures , 1972 .

[17]  Petar N Petrov,et al.  Measurement-based estimation of global pupil functions in 3D localization microscopy. , 2017, Optics express.

[18]  Adam S. Backer,et al.  Extending Single-Molecule Microscopy Using Optical Fourier Processing , 2014, The journal of physical chemistry. B.

[19]  A. Jesacher,et al.  Three-dimensional localization microscopy using deep learning. , 2018, Optics express.

[20]  Yonina C. Eldar,et al.  Phase Retrieval with Application to Optical Imaging: A contemporary overview , 2015, IEEE Signal Processing Magazine.

[21]  Adam S. Backer,et al.  Optimal point spread function design for 3D imaging. , 2014, Physical review letters.

[22]  D. Mnyama,et al.  Improving Initial Phase Estimates for Phase Retrieval Algorithms , 1985 .

[23]  Emmanuel Beaurepaire,et al.  Accuracy of correction in modal sensorless adaptive optics. , 2012, Optics express.

[24]  Y. Shechtman,et al.  Three-Dimensional Localization of Single Molecules for Super-Resolution Imaging and Single-Particle Tracking. , 2017, Chemical reviews.

[25]  D. P. Fromm,et al.  Methods of single-molecule fluorescence spectroscopy and microscopy , 2003 .

[26]  James R Fienup,et al.  Machine learning for improved image-based wavefront sensing. , 2018, Optics letters.

[27]  H. Flyvbjerg,et al.  Optimized localization-analysis for single-molecule tracking and super-resolution microscopy , 2010, Nature Methods.

[28]  Sean Quirin,et al.  Optimal 3D single-molecule localization for superresolution microscopy with aberrations and engineered point spread functions , 2011, Proceedings of the National Academy of Sciences.

[29]  George Barbastathis,et al.  Low Photon Count Phase Retrieval Using Deep Learning. , 2018, Physical review letters.

[30]  Matthew D. Lew,et al.  Correcting field-dependent aberrations with nanoscale accuracy in three-dimensional single-molecule localization microscopy. , 2015, Optica.

[31]  T. Yan,et al.  Computational correction of spatially variant optical aberrations in 3D single-molecule localization microscopy. , 2019, Optics express.